add new models
Browse files- app.py +1 -1
- context_window.json +8 -8
app.py
CHANGED
@@ -519,7 +519,7 @@ with gr.Blocks() as app:
|
|
519 |
# ⚔️ Software Engineering (SE) Arena: Explore and Test the Best SE Chatbots with Long-Context Interactions
|
520 |
|
521 |
## 📜How It Works
|
522 |
-
- **Blind Comparison**: Submit a SE-related query to two anonymous chatbots randomly selected from up to {len(available_models)} top models, including OpenAI, Gemini, Claude, Deepseek, Llama,
|
523 |
- **Interactive Voting**: Engage in multi-turn dialogues with both chatbots and compare their responses. You can continue the conversation until you confidently choose the better model.
|
524 |
- **Fair Play Rules**: Votes are counted only if chatbot identities remain anonymous. Revealing a chatbot's identity disqualifies the session.
|
525 |
|
|
|
519 |
# ⚔️ Software Engineering (SE) Arena: Explore and Test the Best SE Chatbots with Long-Context Interactions
|
520 |
|
521 |
## 📜How It Works
|
522 |
+
- **Blind Comparison**: Submit a SE-related query to two anonymous chatbots randomly selected from up to {len(available_models)} top models, including OpenAI-o3, Gemini-2.0, Claude-3.5, Deepseek-r1, Llama-3.3, Qwen-2.5, and others.
|
523 |
- **Interactive Voting**: Engage in multi-turn dialogues with both chatbots and compare their responses. You can continue the conversation until you confidently choose the better model.
|
524 |
- **Fair Play Rules**: Votes are counted only if chatbot identities remain anonymous. Revealing a chatbot's identity disqualifies the session.
|
525 |
|
context_window.json
CHANGED
@@ -1,17 +1,18 @@
|
|
1 |
{
|
2 |
"gpt-3.5-turbo": 16000,
|
3 |
-
"gpt-3.5-turbo-16k": 16000,
|
4 |
-
"gpt-4-32k": 32000,
|
5 |
"gpt-4-turbo": 128000,
|
6 |
"gpt-4o": 128000,
|
7 |
"gpt-4o-mini": 128000,
|
8 |
-
"claude-3-5-
|
|
|
|
|
9 |
"deepseek-chat": 64000,
|
10 |
"deepseek-r1": 64000,
|
11 |
-
"gemini-1.5-flash
|
12 |
-
"gemini-1.5-pro
|
13 |
-
"
|
14 |
-
"
|
|
|
15 |
"llama-3.1-405b": 128000,
|
16 |
"llama-3.1-70b": 128000,
|
17 |
"llama-3.3-70b": 128000,
|
@@ -23,6 +24,5 @@
|
|
23 |
"Qwen2.5-72B-Instruct": 131072,
|
24 |
"Qwen2.5-72B-Instruct-128k": 131072,
|
25 |
"Qwen2.5-Coder-32B-Instruct": 131072,
|
26 |
-
"QwQ-32B-Preview": 32768,
|
27 |
"yi-large": 32000
|
28 |
}
|
|
|
1 |
{
|
2 |
"gpt-3.5-turbo": 16000,
|
|
|
|
|
3 |
"gpt-4-turbo": 128000,
|
4 |
"gpt-4o": 128000,
|
5 |
"gpt-4o-mini": 128000,
|
6 |
+
"claude-3-5-haiku-20241022" : 200000,
|
7 |
+
"claude-3-5-sonnet-20241022" : 200000,
|
8 |
+
"claude-3-opus-20240229" : 200000,
|
9 |
"deepseek-chat": 64000,
|
10 |
"deepseek-r1": 64000,
|
11 |
+
"gemini-1.5-flash": 1048576,
|
12 |
+
"gemini-1.5-pro": 2097152,
|
13 |
+
"gemini-2.0-flash-lite-preview": 1048576,
|
14 |
+
"gemini-2.0-pro-exp": 2097152,
|
15 |
+
"llama-3.1-8b": 128000,
|
16 |
"llama-3.1-405b": 128000,
|
17 |
"llama-3.1-70b": 128000,
|
18 |
"llama-3.3-70b": 128000,
|
|
|
24 |
"Qwen2.5-72B-Instruct": 131072,
|
25 |
"Qwen2.5-72B-Instruct-128k": 131072,
|
26 |
"Qwen2.5-Coder-32B-Instruct": 131072,
|
|
|
27 |
"yi-large": 32000
|
28 |
}
|